Anoop Deoras

Linbo Liu, Xinle Liu, Qiang Zhou et al. · amazon-science

With the rapid advancement of powerful large language models (LLMs) in recent years, a wide range of software engineering tasks can now be addressed using LLMs, significantly enhancing productivity and scalability. Numerous benchmark datasets have been developed to evaluate the coding capabilities of these models, while they primarily focus on code generation and issue-resolution tasks. In contrast, we introduce a new coding benchmark MigrationBench with a distinct focus: code migration. MigrationBench aims to serve as a comprehensive benchmark for migration from Java 8 to the latest long-term support (LTS) versions (Java 17, 21), including a full dataset and its subset selected with 5,102 and 300 repositories respectively. selected is a representative subset curated for complexity and difficulty, offering a versatile resource to support research in the field of code migration. Additionally, we provide a comprehensive evaluation framework to facilitate rigorous and standardized assessment of LLMs on this challenging task. We further propose an agentic framework and demonstrate that LLMs can effectively tackle repository-level code migration to Java 17. For the selected subset with Claude-4.5-Sonnet, our agentic framework achieves 71.67% and 53.33% success rate (pass@1) for minimal and maximal migration respectively. The dataset and evaluation source code are available at: https://huggingface.co/collections/AmazonScience/migrationbench and https://github.com/amazon-science/MigrationBench respectively.

Amazon AGI, Aaron Langford, Aayush Shah et al. · amazon-science

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks. Amazon Nova Lite is a low-cost multimodal model that is lightning fast for processing images, video, documents and text. Amazon Nova Micro is a text-only model that delivers our lowest-latency responses at very low cost. Amazon Nova Canvas is an image generation model that creates professional grade images with rich customization controls. Amazon Nova Reel is a video generation model offering high-quality outputs, customization, and motion control. Our models were built responsibly and with a commitment to customer trust, security, and reliability. We report benchmarking results for core capabilities, agentic performance, long context, functional adaptation, runtime performance, and human evaluation.

Siddhartha Jain, Xiaofei Ma, Anoop Deoras et al. · amazon-science

Large Language Models (LLMs) can exhibit considerable variation in the quality of their sampled outputs. Reranking and selecting the best generation from the sampled set is a popular way of obtaining strong gains in generation quality. In this paper, we present a novel approach for reranking LLM generations. Unlike other techniques that might involve additional inferences or training a specialized reranker, our approach relies on easy to compute pairwise statistics between the generations that have minimal compute overhead. We show that our approach can be formalized as an extension of self-consistency and analyze its performance in that framework, theoretically as well as via simulations. We show strong improvements for selecting the best k generations for code generation tasks as well as robust improvements for the best generation for the tasks of autoformalization, summarization, and translation. While our approach only assumes black-box access to LLMs, we show that additional access to token probabilities can improve performance even further.

Trong Nghia Hoang, Anoop Deoras, Tong Zhao et al.

This paper studies the item-to-item recommendation problem in recommender systems from a new perspective of metric learning via implicit feedback. We develop and investigate a personalizable deep metric model that captures both the internal contents of items and how they were interacted with by users. There are two key challenges in learning such model. First, there is no explicit similarity annotation, which deviates from the assumption of most metric learning methods. Second, these approaches ignore the fact that items are often represented by multiple sources of meta data and different users use different combinations of these sources to form their own notion of similarity. To address these challenges, we develop a new metric representation embedded as kernel parameters of a probabilistic model. This helps express the correlation between items that a user has interacted with, which can be used to predict user interaction with new items. Our approach hinges on the intuition that similar items induce similar interactions from the same user, thus fitting a metric-parameterized model to predict an implicit feedback signal could indirectly guide it towards finding the most suitable metric for each user. To this end, we also analyze how and when the proposed method is effective from a theoretical lens. Its empirical effectiveness is also demonstrated on several real-world datasets.

Anusha Lalitha, Kousha Kalantari, Yifei Ma et al.

We study the problem of best-arm identification (BAI) in the fixed-budget setting with heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this setting: SHVar for known reward variances and SHAdaVar for unknown reward variances. Our algorithms rely on non-uniform budget allocations among the arms where the arms with higher reward variances are pulled more often than those with lower variances. The main algorithmic novelty is in the design of SHAdaVar, which allocates budget greedily based on overestimating the unknown reward variances. We bound probabilities of misidentifying the best arms in both SHVar and SHAdaVar. Our analyses rely on novel lower bounds on the number of pulls of an arm that do not require closed-form solutions to the budget allocation problem. Since one of our budget allocation problems is analogous to the optimal experiment design with unknown variances, we believe that our results are of a broad interest. Our experiments validate our theory, and show that SHVar and SHAdaVar outperform algorithms from prior works with analytical guarantees.

Ziqian Lin, Hao Ding, Nghia Trong Hoang et al.

Recent studies on pre-trained vision/language models have demonstrated the practical benefit of a new, promising solution-building paradigm in AI where models can be pre-trained on broad data describing a generic task space and then adapted successfully to solve a wide range of downstream tasks, even when training data is severely limited (e.g., in zero- or few-shot learning scenarios). Inspired by such progress, we investigate in this paper the possibilities and challenges of adapting such a paradigm to the context of recommender systems, which is less investigated from the perspective of pre-trained model. In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data). However, unlike vision/language data which share strong conformity in the semantic space, universal patterns underlying recommendation data collected across different domains (e.g., different countries or different E-commerce platforms) are often occluded by both in-domain and cross-domain biases implicitly imposed by the cultural differences in their user and item bases, as well as their uses of different e-commerce platforms. As shown in our experiments, such heterogeneous biases in the data tend to hinder the effectiveness of the pre-trained model. To address this challenge, we further introduce and formalize a causal debiasing perspective, which is substantiated via a hierarchical Bayesian deep learning model, named PreRec. Our empirical studies on real-world data show that the proposed model could significantly improve the recommendation performance in zero- and few-shot learning settings under both cross-market and cross-platform scenarios.

Ziwei Fan, Hao Ding, Anoop Deoras et al.

Item-to-Item (I2I) recommendation is an important function in most recommendation systems, which generates replacement or complement suggestions for a particular item based on its semantic similarities to other cataloged items. Given that subsets of items in a recommendation system might be co-interacted with by the same set of customers, graph-based models, such as graph neural networks (GNNs), provide a natural framework to combine, ingest and extract valuable insights from such high-order relational interactions between cataloged items, as well as their metadata features, as has been shown in many recent studies. However, learning GNNs effectively for I2I requires ingesting a large amount of relational data, which might not always be available, especially in new, emerging market segments. To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing mature market segments (with private data) could be adapted to build effective warm-start models for emerging ones. To achieve this, we propose and investigate a personalized federated modeling framework based on GNNs to summarize, assemble and adapt recommendation patterns across market segments with heterogeneous customer behaviors into effective local models. Our key contribution is a personalized graph adaptation model that bridges the gap between recent literature on federated GNNs and (non-graph) personalized federated learning, which either does not optimize for the adaptability of the federated model or is restricted to local models with homogeneous parameterization, excluding GNNs with heterogeneous local graphs.

Vijay Lingam, Aditya Golatkar, Anwesan Pal et al.

For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize expensive reasoning into reusable intermediate representations. We study a broad class of such systems, termed Guide-Core Policies (GCoP), in which a guide model generates a structured strategy that is executed by a black-box core model. This abstraction subsumes base, supervised, and advisor-style approaches, which differ primarily in how the guide is trained. We formalize GCoP under a cost-sensitive utility objective and show that end-to-end performance is governed by guide-averaged executability: the probability that a strategy generated by the guide can be faithfully executed by the core. Our analysis shows that existing GCoP instantiations often fail to optimize executability under deployment constraints, resulting in brittle strategies and inefficient computation. Motivated by these insights, we propose ExecTune, a principled training recipe that combines teacher-guided acceptance sampling, supervised fine-tuning, and structure-aware reinforcement learning to directly optimize syntactic validity, execution success, and cost efficiency. Across mathematical reasoning and code-generation benchmarks, GCoP with ExecTune improves accuracy by up to 9.2% over prior state-of-the-art baselines while reducing inference cost by up to 22.4%. It enables Claude Haiku 3.5 to outperform Sonnet 3.5 on both math and code tasks, and to come within 1.7% absolute accuracy of Sonnet 4 at 38% lower cost. Beyond efficiency, GCoP also supports modular adaptation by updating the guide without retraining the core.

Prithwish Jana, Sam Davidson, Bhavana Bhasker et al.

Automating Infrastructure-as-Code (IaC) is challenging, and large language models (LLMs) often produce incorrect configurations from natural language (NL). We present TerraFormer, a neuro-symbolic framework for IaC generation and mutation that combines supervised fine-tuning with verifier-guided reinforcement learning, using formal verification tools to provide feedback on syntax, deployability, and policy compliance. We curate two large, high-quality NL-to-IaC datasets, TF-Gen (152k instances) and TF-Mutn (52k instances), via multi-stage verification and iterative LLM self-correction. Evaluations against 17 state-of-the-art LLMs, including ~50x larger models like Sonnet 3.7, DeepSeek-R1, and GPT-4.1, show that TerraFormer improves correctness over its base LLM by 15.94% on IaC-Eval, 11.65% on TF-Gen (Test), and 19.60% on TF-Mutn (Test). It outperforms larger models on both TF-Gen (Test) and TF-Mutn (Test), ranks third on IaC-Eval, and achieves top best-practices and security compliance.

Chanakya Ekbote, Vijay Lingam, Behrooz Omidvar-Tehrani et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful framework for enhancing the reasoning capabilities of large language models (LLMs). However, existing approaches such as Group Relative Policy Optimization (GRPO) and its variants, while effective on reasoning benchmarks, struggle with agentic tasks that require iterative decision-making. We introduce Murphy, a multi-turn reflective optimization framework that extends GRPO by incorporating iterative self-correction during training. By leveraging both quantitative and qualitative execution feedback, Murphy enables models to progressively refine their reasoning across multiple turns. Evaluations on code generation benchmarks with model families such as Qwen and OLMo show that Murphy consistently improves performance, achieving up to a 8% relative gain in pass@1 over GRPO, on similar compute budgets.

Mostafa Rahmani, Anoop Deoras, Laurent Callot

This paper presents a novel, closed-form, and data/computation efficient online anomaly detection algorithm for time-series data. The proposed method, dubbed RPE, is a window-based method and in sharp contrast to the existing window-based methods, it is robust to the presence of anomalies in its window and it can distinguish the anomalies in time-stamp level. RPE leverages the linear structure of the trajectory matrix of the time-series and employs a robust projection step which makes the algorithm able to handle the presence of multiple arbitrarily large anomalies in its window. A closed-form/non-iterative algorithm for the robust projection step is provided and it is proved that it can identify the corrupted time-stamps. RPE is a great candidate for the applications where a large training data is not available which is the common scenario in the area of time-series. An extensive set of numerical experiments show that RPE can outperform the existing approaches with a notable margin.

Yating Wu, Yuhao Zhang, Sayan Ghosh et al.

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured information that later steps rely on. Recent retrieval-based memory systems surface relevant content but still overlook the causal and logical structure needed for multi-step reasoning. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. Unlike prior context management approaches, ContextWeaver supports: (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summarization that condenses root-to-step reasoning paths into reusable units; and (3) a lightweight validation layer that incorporates execution feedback. On the SWE-Bench Verified and Lite benchmarks, ContextWeaver improves performance over a sliding-window baseline in pass@1, while reducing reasoning steps and token usage. Our observations suggest that modeling logical dependencies provides a stable and scalable memory mechanism for LLM agents that use tools.

Gauthier Guinet, Behrooz Omidvar-Tehrani, Anoop Deoras et al. · amazon-science

We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions based on the corpus of documents associated with the task. Our method is an automated, cost-efficient, interpretable, and robust strategy to select the optimal components for a RAG system. We leverage Item Response Theory (IRT) to estimate the quality of an exam and its informativeness on task-specific accuracy. IRT also provides a natural way to iteratively improve the exam by eliminating the exam questions that are not sufficiently informative about a model's ability. We demonstrate our approach on four new open-ended Question-Answering tasks based on Arxiv abstracts, StackExchange questions, AWS DevOps troubleshooting guides, and SEC filings. In addition, our experiments reveal more general insights into factors impacting RAG performance like size, retrieval mechanism, prompting and fine-tuning. Most notably, our findings show that choosing the right retrieval algorithms often leads to bigger performance gains than simply using a larger language model.

Hantian Ding, Zijian Wang, Giovanni Paolini et al. · amazon-science

In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens. Despite its efficiency, the concatenation approach compromises data integrity -- it inevitably breaks many documents into incomplete pieces, leading to excessive truncations that hinder the model from learning to compose logically coherent and factually consistent content that is grounded on the complete context. To address the issue, we propose Best-fit Packing, a scalable and efficient method that packs documents into training sequences through length-aware combinatorial optimization. Our method completely eliminates unnecessary truncations while retaining the same training efficiency as concatenation. Empirical results from both text and code pre-training show that our method achieves superior performance (e.g., relatively +4.7% on reading comprehension; +16.8% in context following; and +9.2% on program synthesis), and reduces closed-domain hallucination effectively by up to 58.3%.

Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha et al. · amazon-science

Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges. This paper describes a system of batched speculative decoding that sets a new state of the art in multi-sequence generation latency and that demonstrates superior GPU utilization as well as quality of generations within a time budget. For example, for a 7.8B-size model on a single A100 GPU and with a batch size of 8, each sequence is generated at an average speed of 5.8ms per token, the overall throughput being 1.1K tokens per second. These results represent state-of-the-art latency and a 2.15X speed-up over optimized regular decoding. Within a time budget that regular decoding does not finish, our system is able to generate sequences with HumanEval Pass@First of 43% and Pass@All of 61%, far exceeding what's feasible with single-sequence speculative decoding. Our peak GPU utilization during decoding reaches as high as 15.8%, more than 3X the highest of that of regular decoding and around 10X of single-sequence speculative decoding.

Behnam Rahdari, Hao Ding, Ziwei Fan et al.

The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most existing models struggle to produce zero-shot explanations reliably. To address this issue, we propose a framework called Logic-Scaffolding, that combines the ideas of aspect-based explanation and chain-of-thought prompting to generate explanations through intermediate reasoning steps. In this paper, we share our experience in building the framework and present an interactive demonstration for exploring our results.

Yuhao Zhang, Shiqi Wang, Haifeng Qian et al.

Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation models is crucial to enhancing user experience in real-world applications, existing research efforts do not address this issue. To fill this gap, we propose CodeFort, a framework to improve the robustness of code generation models, generalizing a large variety of code perturbations to enrich the training data and enabling various robust training strategies, mixing data augmentation, batch augmentation, adversarial logits pairing, and contrastive learning, all carefully designed to support high-throughput training. Extensive evaluations show that we increase the average robust pass rates of baseline CodeGen models from 14.79 to 21.74. We notably decrease the robustness drop rate from 95.02% to 54.95% against code-syntax perturbations.

Sachit Kuhar, Wasi Uddin Ahmad, Zijian Wang et al.

Recent advancements in code completion models have primarily focused on local file contexts. However, these studies do not fully capture the complexity of real-world software development, which often requires the use of rapidly-evolving public libraries. To fill the gap, we introduce LibEvolutionEval, a detailed study requiring an understanding of library evolution to perform in-line code completion accurately. LibEvolutionEval provides a version-specific code-completion task comprised of eight libraries (torch, torchvision, scipy, pil, tqdm, pyyaml, matplotlib, and pandas) as they evolve over the year along with a detailed analysis of the evolution of two popular and well-maintained public libraries: PyTorch and Matplotlib. We evaluate popular public models and find that public library evolution significantly influences model performance. We explored mitigation methods by studying how retrieved version-specific library documentation and prompting can improve the model's capability in handling these fast-evolving packages, paving a promising future path in better handling fast-evolving libraries.

Myeongsoo Kim, Shweta Garg, Baishakhi Ray et al. · amazon-science

Programming assistants powered by large language models have transformed software development, yet most benchmarks focus narrowly on code generation tasks. Recent efforts like InfiBench and StackEval attempt to address this gap using Stack Overflow data but remain limited to single-turn interactions in isolated contexts, require significant manual curation, and fail to represent complete project environments. We introduce CodeAssistBench (CAB), the first benchmark framework for evaluating multi-turn programming assistance in realistic settings that address real-world questions about actual codebases. Unlike existing programming Q&A benchmarks, CAB automatically generates scalable datasets from question-related GitHub issues using configurable parameters (e.g., repository creation date, star count, programming languages), and includes automatic containerization of codebases for evaluation. It then evaluates models through simulated users in these containerized environments with full codebase access. Using this framework, we constructed a test set of 3,286 real-world programming questions across 231 repositories, spanning seven programming languages and diverse problem domains. Our evaluation of leading LLMs reveals a substantial capability gap: while models perform well on Stack Overflow questions with success rates of 70-83%, they resolve only up to 16.49% of CAB's recent issues. This discrepancy highlights the challenges of providing assistance in complex, project-specific contexts versus answering standalone questions.

Yifeng Ding, Hung Le, Songyang Han et al.

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Optimization (GRPO), suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. To address this issue, we propose Group Turn Policy Optimization (GTPO), a novel RL algorithm specifically designed for training LLMs on multi-turn TIR tasks. GTPO introduces three key innovations: (1) turn-level reward assignment that provides fine-grained feedback for individual turns, (2) return-based advantage estimation where normalized discounted returns are calculated as advantages, and (3) self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. Our comprehensive evaluation demonstrates that GTPO outperforms GRPO by 3.0% on average across diverse reasoning benchmarks, establishing its effectiveness for advancing complex mathematical reasoning in the real world.

Sam Davidson, Li Sun, Bhavana Bhasker et al.

Infrastructure as Code (IaC) is fundamental to modern cloud computing, enabling teams to define and manage infrastructure through machine-readable configuration files. However, different cloud service providers utilize diverse IaC formats. The lack of a standardized format requires cloud architects to be proficient in multiple IaC languages, adding complexity to cloud deployment. While Large Language Models (LLMs) show promise in automating IaC creation and maintenance, progress has been limited by the lack of comprehensive benchmarks across multiple IaC formats. We present Multi-IaC-Bench, a novel benchmark dataset for evaluating LLM-based IaC generation and mutation across AWS CloudFormation, Terraform, and Cloud Development Kit (CDK) formats. The dataset consists of triplets containing initial IaC templates, natural language modification requests, and corresponding updated templates, created through a synthetic data generation pipeline with rigorous validation. We evaluate several state-of-the-art LLMs on Multi-IaC-Bench, demonstrating that while modern LLMs can achieve high success rates (>95%) in generating syntactically valid IaC across formats, significant challenges remain in semantic alignment and handling complex infrastructure patterns. Our ablation studies highlight the importance of prompt engineering and retry mechanisms in successful IaC generation. We release Multi-IaC-Bench to facilitate further research in AI-assisted infrastructure management and establish standardized evaluation metrics for this crucial domain.

John Harvill, Ziwei Fan, Hao Wang et al.

Existing work on prompt compression for Large Language Models (LLM) focuses on lossy methods that try to maximize the retention of semantic information that is relevant to downstream tasks while significantly reducing the sequence length. In this paper, we introduce a task-agnostic lossless compression technique similar to LZ77 that makes it possible to reduce the input token sequence length on average by 27\% and 18\% for the two evaluation tasks explored here. Given that we use transformer-based LLMs, this equates to 47\% and 33\% less encoding computation, respectively, due to the quadratic nature of attention. The token sequence transformation is trivial to reverse and highlights that no semantic information is lost in the process. We evaluate our proposed approach on two tasks that require strict preservation of semantics/syntax and demonstrate that existing lossy compression methods perform poorly in this setting. We find that our lossless compression technique produces only a small gap in performance compared to using the uncompressed input and posit that larger models and an expanded computing budget would likely erase the gap entirely.

Tao Yu, Gaurav Gupta, Karthick Gopalswamy et al.

Large models training is plagued by the intense compute cost and limited hardware memory. A practical solution is low-precision representation but is troubled by loss in numerical accuracy and unstable training rendering the model less useful. We argue that low-precision floating points can perform well provided the error is properly compensated at the critical locations in the training process. We propose Collage which utilizes multi-component float representation in low-precision to accurately perform operations with numerical errors accounted. To understand the impact of imprecision to training, we propose a simple and novel metric which tracks the lost information during training as well as differentiates various precision strategies. Our method works with commonly used low-precision such as half-precision ($16$-bit floating points) and can be naturally extended to work with even lower precision such as $8$-bit. Experimental results show that pre-training using Collage removes the requirement of using $32$-bit floating-point copies of the model and attains similar/better training performance compared to $(16, 32)$-bit mixed-precision strategy, with up to $3.7\times$ speedup and $\sim 15\%$ to $23\%$ less memory usage in practice.

Hao Ding, Yifei Ma, Anoop Deoras et al.

Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS. On the other hand, zero-shot learning promises some degree of generalization from an old dataset to an entirely new dataset. In this paper, we explore the possibility of zero-shot learning in RS. We develop an algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor overlapping items, a setting that contrasts typical cross-domain RS that has either overlapping users or items. Different from categorical item indices, i.e., item ID, in previous methods, ZESRec uses items' natural-language descriptions (or description embeddings) as their continuous indices, and therefore naturally generalize to any unseen items. In terms of users, ZESRec builds upon recent advances on sequential RS to represent users using their interactions with items, thereby generalizing to unseen users as well. We study three pairs of real-world RS datasets and demonstrate that ZESRec can successfully enable recommendations in such a zero-shot setting, opening up new opportunities for resolving the chicken-and-egg problem for data-scarce startups or early-stage products.